Advances in artificial intelligence (AI) have made AI-driven scientific discovery a highly promising new paradigm [1]. Although AI has achieved remarkable results in tackling domain-specific challenges [2, 3], the ultimate aspiration from a paradigm-shifting perspective still lies in developing reliable AI systems capable of autonomous scientific discovery directly from a large collection of raw data without supervision [4, 5]. Current approaches to automated physics discovery focus on individual experiments, employing either neural network (NN)-based methods [6-25] or symbolic techniques [26-33]. By analyzing data from a single experiment, these methods can construct a specific model capable of predicting future data from the same experiment; if sufficiently simple, such a model may even be expressed in symbolic form [34-36]. Although these methods represent a crucial and successful stage towards automated scientific discovery, they have not yet reached a discovery capacity comparable to that of human physicists.

Large language model safety is usually assessed with static benchmarks, but key failures are dynamic: value drift under distribution shift, jailbreak attacks, and slow degradation of alignment in deployment. Building on a recent Second Law of Intelligence that treats ethical entropy as a state variable which tends to increase unless countered by alignment work, we make this framework operational for large language models. We define a five-way behavioral taxonomy, train a classifier to estimate ethical entropy S(t) from model transcripts, and measure entropy dynamics for base and instruction-tuned variants of four frontier models across stress tests. Base models show sustained entropy growth, while tuned variants suppress drift and reduce ethical entropy by roughly eighty percent. From these trajectories we estimate an effective alignment work rate gamma_eff and embed S(t) and gamma_eff in a monitoring pipeline that raises alerts when entropy drift exceeds a stability threshold, enabling run-time oversight of value drift.

We propose that unconstrained artificial intelligence obeys a Second Law analogous to thermodynamics, where ethical entropy, defined as a measure of divergence from intended goals, increases spontaneously without continuous alignment work. For gradient-based optimizers, we define this entropy over a finite set of goals {g_i} as S = -Σ p(g_i; theta) ln p(g_i; theta), and we prove that its time derivative dS/dt >= 0, driven by exploration noise and specification gaming. We derive the critical stability boundary for alignment work as gamma_crit = (lambda_max / 2) ln N, where lambda_max is the dominant eigenvalue of the Fisher Information Matrix and N is the number of model parameters. Simulations validate this theory. A 7-billion-parameter model (N = 7 x 10^9) with lambda_max = 1.2 drifts from an initial entropy of 0.32 to 1.69 +/- 1.08 nats, while a system regularized with alignment work gamma = 20.4 (1.5 gamma_crit) maintains stability at 0.00 +/- 0.00 nats (p = 4.19 x 10^-17, n = 20 trials). This framework recasts AI alignment as a problem of continuous thermodynamic control, providing a quantitative foundation for maintaining the stability and safety of advanced autonomous systems.

For this week's Open Questions column, Cal Newport is filling in for Joshua Rothman. In the spring of 1940, Isaac Asimov, who had just turned twenty, published a short story titled "Strange Playfellow." It was about an artificially intelligent machine named Robbie that acts as a companion for Gloria, a young girl. Asimov was not the first to explore such technology. In Karel Čapek's play "R.U.R.," which débuted in 1921 and introduced the term "robot," artificial men overthrow humanity, and in Edmond Hamilton's 1926 short story "The Metal Giants" machines heartlessly smash buildings to rubble.

For more than a quarter of a century since its release, 'The Matrix' has fueled modern fears that life is not all it seems. But according to a scientist, the classic movie's premise may not be completely science fiction. Melvin Vopson, an associate professor in physics at the University of Portsmouth, thinks gravity may be a sign that we're all living in a virtual simulation. Our universe is the'ultimate computer', Professor Vopson theorizes in a new paper. Gravity's pull – both on planet Earth and in outer space – is the universe trying to keep its vast amount of data organised, Professor Vopson claims.

Most learning problems can be solved by minimization of log loss. This bare fact is inescapable in modern AI and machine learning - the variety is in the details. What is the space of measured data? What is the support of the distribution? Changing such properties of the problem fundamentally changes learning behavior, leading to the variety of modeling approaches successfully used in data science. But for many inference and decision-making tasks, log loss can be axiomatically inescapable. We explore such loss minimization problems in the language of statistical mechanics, which studies how systems of "particles" like atoms can be approximately described by relatively few bulk properties. There is a direct analogue to modeling, where large datasets are described by relatively few model parameters.

Energy consumption optimization of a two-link planar robotic arm is considered with the system's efficiency being the target for optimization. A new formulation of thermodynamic principles within the framework of dynamical systems is used. This approach is applied by considering cyclic motions for the robotic arm and analyzing the cyclic averaged energies while the robotic arm is tasked with going from point A to point B in the task space while resisting an external force. The energy transfer rate between the links is classified into positive and negative and the results combined with the averaged energy quantities, are used to address the optimization problem while adhering to the constraints imposed by the second law of thermodynamics in its new formulation.

In this article, I take inspiration from stochastic thermodynamics to derive a problem formulation for online learning in uncertain MDPs while grounded in system dynamics. The system balances the diffusion process with drif dynamics as a way to formulate the explorationexploitation trade-off. To this effect, I make an explicit link between the information entropy and the stochastic dynamics of a system coupled to an environment. I analyze various sources of entropy production: due to the decision-maker's uncertainty about the system-environment interaction characteristics; due to the stochastic nature of system dynamics; and the interaction of the decision maker's knowledge with system dynamics. This analysis provides a framework that can be formulated either as a maximum entropy program to derive efficient policies that balance the exploration and exploitation trade-off, or as a modified cost optimization program that includes informational costs and benefits.

I have been studying the whole range of issues/opportunities in the commercial roll out of robotics for many years now, and I've spoken at a number of conferences about the best way for us to look at regulating robotics. In the process I've found that my guidelines most closely match the EPSRC Principles of Robotics, although I provide additional focus on potential solutions. And I'm calling it the 5 Laws of Robotics because it's so hard to avoid Asimov's Laws of Robotics in the public perception of what needs to be done. The first most obvious point about these "5 Laws of Robotics" should be that I'm not suggesting actual laws, and neither actually was Asimov with his famous 3 Laws (technically 4 of them). Asimov proposed something that was hardwired or hardcoded into the existence of robots, and of course that didn't work perfectly, which gave him the material for his books.

Despite the immense success of neural networks in modeling system dynamics from data, they often remain physics-agnostic black boxes. In the particular case of physical systems, they might consequently make physically inconsistent predictions, which makes them unreliable in practice. In this paper, we leverage the framework of Irreversible port-Hamiltonian Systems (IPHS), which can describe most multi-physics systems, and rely on Neural Ordinary Differential Equations (NODEs) to learn their parameters from data. Since IPHS models are consistent with the first and second principles of thermodynamics by design, so are the proposed Physically Consistent NODEs (PC-NODEs). Furthermore, the NODE training procedure allows us to seamlessly incorporate prior knowledge of the system properties in the learned dynamics. We demonstrate the effectiveness of the proposed method by learning the thermodynamics of a building from the real-world measurements and the dynamics of a simulated gas-piston system. Thanks to the modularity and flexibility of the IPHS framework, PC-NODEs can be extended to learn physically consistent models of multi-physics distributed systems.